1. |
|
|
2. |
- Canelhas, Daniel R., 1983-, et al.
(author)
-
Compressed Voxel-Based Mapping Using Unsupervised Learning
- 2017
-
In: Robotics. - Basel, Switzerland : MDPI AG. - 2218-6581. ; 6:3
-
Journal article (peer-reviewed)abstract
- In order to deal with the scaling problem of volumetric map representations, we propose spatially local methods for high-ratio compression of 3D maps, represented as truncated signed distance fields. We show that these compressed maps can be used as meaningful descriptors for selective decompression in scenarios relevant to robotic applications. As compression methods, we compare using PCA-derived low-dimensional bases to nonlinear auto-encoder networks. Selecting two application-oriented performance metrics, we evaluate the impact of different compression rates on reconstruction fidelity as well as to the task of map-aided ego-motion estimation. It is demonstrated that lossily reconstructed distance fields used as cost functions for ego-motion estimation can outperform the original maps in challenging scenarios from standard RGB-D (color plus depth) data sets due to the rejection of high-frequency noise content.
|
|
3. |
- Canelhas, Daniel R., 1983-, et al.
(author)
-
From Feature Detection in Truncated Signed Distance Fields to Sparse Stable Scene Graphs
- 2016
-
In: IEEE Robotics and Automation Letters. - Piscataway, USA : Institute of Electrical and Electronics Engineers (IEEE). - 2377-3766. ; 1:2, s. 1148-1155
-
Journal article (peer-reviewed)abstract
- With the increased availability of GPUs and multicore CPUs, volumetric map representations are an increasingly viable option for robotic applications. A particularly important representation is the truncated signed distance field (TSDF) that is at the core of recent advances in dense 3D mapping. However, there is relatively little literature exploring the characteristics of 3D feature detection in volumetric representations. In this paper we evaluate the performance of features extracted directly from a 3D TSDF representation. We compare the repeatability of Integral invariant features, specifically designed for volumetric images, to the 3D extensions of Harris and Shi & Tomasi corners. We also study the impact of different methods for obtaining gradients for their computation. We motivate our study with an example application for building sparse stable scene graphs, and present an efficient GPU-parallel algorithm to obtain the graphs, made possible by the combination of TSDF and 3D feature points. Our findings show that while the 3D extensions of 2D corner-detection perform as expected, integral invariants have shortcomings when applied to discrete TSDFs. We conclude with a discussion of the cause for these points of failure that sheds light on possible mitigation strategies.
|
|